HYDRA: Revealing heterogeneity of imaging and genetic patterns through a multiple max-margin discriminative analysis framework

Erdem Varol, Aristeidis Sotiras, Christos DavatzikosNeuroImage 2017 · DOI · OpenReview

Abstract

Highlights•We present a novel machine learning framework for the analysis of heterogeneity in neuroimaging studies.•We propose a semi-supervised learning framework that integrates classification and clustering.•The anatomical and genetic heterogeneity of Alzheimer's disease is explored using the proposed framework.•The anatomical and genetic subtypes that are revealed are clinically meaningful and match well with previous studies.
BibTeX
@article{varol2017hydra,
  author = {Erdem Varol and Aristeidis Sotiras and Christos Davatzikos},
  title = {{HYDRA: Revealing heterogeneity of imaging and genetic patterns through a multiple max-margin discriminative analysis framework}},
  journal = {NeuroImage},
  year = {2017},
  doi = {10.1016/j.neuroimage.2016.02.041},
}

Loading related content...

Figure